© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70391
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates strongly on numeric literals (sequences of digits) in code or text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ּוֹ
    -1.39
    ֶּ
    -1.27
     manualidades
    -1.27
     BufferedWriter
    -1.25
    ־ה
    -1.23
    >
    -1.20
    かしい
    -1.19
    ִּ
    -1.17
     that
    -1.13
     it
    -1.12
    POSITIVE LOGITS
     jogador
    1.26
    Exeunt
    1.19
    3
    1.17
    ῷ
    1.15
    5
    1.14
     thậm
    1.07
    Didier
    1.06
     avanzado
    1.04
    0
    1.04
     unterstützt
    1.02
    Activations Density 0.002%

    No Known Activations